recover_session

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description provides some behavioral transparency by listing actions (diagnose, repair, extract) and the target (corrupted/crashed sessions). However, it fails to disclose potential side effects, permissions required, or what happens to the session file, which are important for a recovery operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two sentences, no redundant words. It front-loads the key action verbs (diagnose, repair, extract) and the use case, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description should ideally mention what the tool returns (e.g., diagnostic info, recovered files) to set expectations. It currently omits this, leaving the agent to guess the output format, which is a gap for a tool that performs potentially complex recovery actions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters. The description merely echoes 'repair' and 'extract' without adding new meaning or usage context beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: diagnose, repair, or extract content from a Claude Code session, specifically for corrupted or crashed sessions. It distinguishes from siblings by focusing on recovery, though it could explicitly differentiate from similar tools like unstick_session.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates when to use the tool ('for corrupted or crashed sessions'), implying usage context. However, it does not provide explicit guidance on when not to use it or suggest alternatives, which limits its usefulness for an AI agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.